statsmodels.tsa.stattools.pacf_burg¶

statsmodels.tsa.stattools.pacf_burg(x, nlags=None, demean=True)[source]¶

Calculate Burg”s partial autocorrelation estimator.

Parameters:¶

x : array_like¶: Observations of time series for which pacf is calculated.
nlags : int, optional¶: Number of lags to return autocorrelation for. If not provided, uses min(10 * np.log10(nobs), nobs - 1).
demean : bool, optional¶: Flag indicating to demean that data. Set to False if x has been previously demeaned.

Returns:¶

pacf (ndarray) – Partial autocorrelations for lags 0, 1, …, nlag.
sigma2 (ndarray) – Residual variance estimates where the value in position m is the residual variance in an AR model that includes m lags.